D.H. Nguyen and B. Widrow (1990) demonstrated that a feedforward neural network can be trained to steer a tractor-trailer truck to a dock while backing up. The feedforward network they used to control the truck contained 25 hidden units and required extensive training. The authors demonstrate that a very simple solution to the truck backer-upper exists and can be found by decomposing the problem into subtasks. By hard-wiring these control laws into a network, they found a controller with only two hidden units that performs as well as the larger controller trained from scratch. This approach could be used to build up more complex controllers from simple components.

September 01 1992 A Simplified Neural-Network Solution through Problem Decomposition: The Case of the Truck Backer-Upper In Special Collection: CogNet Robert E. Jenkins, Robert E. Jenkins The Applied Physics Laboratory, The Johns Hopkins University, Baltimore, MD 21218 USA Search for other works by this author on: This Site Google Scholar Ben P. Yuhas Ben P. Yuhas The Applied Physics Laboratory, The Johns Hopkins University, Baltimore, MD 21218 USA Search for other works by this author on: This Site Google Scholar Author and Article Information Robert E. Jenkins The Applied Physics Laboratory, The Johns Hopkins University, Baltimore, MD 21218 USA Ben P. Yuhas The Applied Physics Laboratory, The Johns Hopkins University, Baltimore, MD 21218 USA *Current address: Bellcore MRE 2E-330, Morristown, NJ 07962-1910 USA. Received: December 17 1991 Accepted: March 04 1992 Online ISSN: 1530-888X Print ISSN: 0899-7667 © 1992 Massachusetts Institute of Technology1992 Neural Computation (1992) 4 (5): 647–649. https://doi.org/10.1162/neco.1992.4.5.647 Article history Received: December 17 1991 Accepted: March 04 1992 Cite Icon Cite Permissions Share Icon Share Facebook Twitter LinkedIn MailTo Views Icon Views Article contents Figures & tables Video Audio Supplementary Data Peer Review Search Site Citation Robert E. Jenkins, Ben P. Yuhas; A Simplified Neural-Network Solution through Problem Decomposition: The Case of the Truck Backer-Upper. Neural Comput 1992; 4 (5): 647–649. doi: https://doi.org/10.1162/neco.1992.4.5.647 Download citation file: Ris (Zotero) Reference Manager EasyBib Bookends Mendeley Papers EndNote RefWorks BibTex toolbar search Search Dropdown Menu toolbar search search input Search input auto suggest filter your search All ContentAll JournalsNeural Computation Search Advanced Search This content is only available as a PDF. © 1992 Massachusetts Institute of Technology1992 Article PDF first page preview Close Modal You do not currently have access to this content.

An overview of the current-mode approach for designing analog VLSI neural systems in subthreshold CMOS technology is presented. Emphasis is given to design techniques at the device level using the current-controlled current conveyor and the translinear principle. Circuits for associative memory and silicon retina systems are used as examples. The design methodology and how it relates to actual biological microcircuits are discussed.

It is demonstrated that multiple sources of speech information can be integrated at a subsymbolic level to improve vowel recognition. Feedforward and recurrent neural networks are trained to estimate the acoustic characteristics of a vocal tract from images of the speaker's mouth. These estimates are then combined with the noise-degraded acoustic information, effectively increasing the signal-to-noise ratio and improving the recognition of these noise-degraded signals. Alternative symbolic strategies such as direct categorization of the visual signals into vowels are also presented. The performances of these neural networks compare favorably with human performance and with other pattern-matching and estimation techniques.>